Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,23 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1344/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1440/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1536/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1632/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1728/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1824/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1900/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-192/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-288/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-384/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-480/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-576/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-672/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-768/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-864/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-96/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-960/tokenizer.json filter=lfs diff=lfs merge=lfs -text

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40a461656ee106d88938fc2c25f046309a279da16d3842382de6386cea94230f
+size 1342239008

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/latest

@@ -0,0 +1 @@
+global_step1050

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc130fdd571117663409ca61bedcc1df721dc1659afd390225217880ffdd2b6
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b48fec0f244d7c7a1bd8e012a0fe6d4efa325f3a0d12c0f4058d2743e82cd08
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41381c550239511d09e6dfde76f1759e58298107d0f17b3d24bbe18641db2da1
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca05e67c9fa321a4247750fb9fb97097cde1abb8b2b1185fb65119acbd691afb
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd266faa633a82743639b67cc84e64266cb4ebc99ec8d2cd6b70d3dc00b202b4
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc65395a054437d1f918fad30aa9f94e92fe59ebed1c62f376817a960e14e40
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fe6fcf16395cf9024f8c14976bf0eeb65f085bc88ebd11d6aecfc43e787c99
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ac73cc239170935c6e1dea9e09507d51ad8f51c1ff8f0fbaab98f5ddb94c0c
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0fa6231cdfa2cdb96b1515d90eeb202726c0936215d0abfcf573959fc66605
+size 1064

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/trainer_state.json

@@ -0,0 +1,1511 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.0,
+  "eval_steps": 500,
+  "global_step": 1056,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05235602094240838,
+      "grad_norm": 1.479238510131836,
+      "learning_rate": 1.2631578947368422e-06,
+      "loss": 1.859,
+      "step": 5
+    },
+    {
+      "epoch": 0.10471204188481675,
+      "grad_norm": 1.949265480041504,
+      "learning_rate": 2.842105263157895e-06,
+      "loss": 1.8637,
+      "step": 10
+    },
+    {
+      "epoch": 0.15706806282722513,
+      "grad_norm": 1.8027445077896118,
+      "learning_rate": 4.421052631578947e-06,
+      "loss": 1.8695,
+      "step": 15
+    },
+    {
+      "epoch": 0.2094240837696335,
+      "grad_norm": 1.3422410488128662,
+      "learning_rate": 6e-06,
+      "loss": 1.7703,
+      "step": 20
+    },
+    {
+      "epoch": 0.2617801047120419,
+      "grad_norm": 1.3363796472549438,
+      "learning_rate": 7.578947368421053e-06,
+      "loss": 1.7696,
+      "step": 25
+    },
+    {
+      "epoch": 0.31413612565445026,
+      "grad_norm": 1.1196855306625366,
+      "learning_rate": 9.157894736842105e-06,
+      "loss": 1.748,
+      "step": 30
+    },
+    {
+      "epoch": 0.36649214659685864,
+      "grad_norm": 1.0649173259735107,
+      "learning_rate": 1.0736842105263158e-05,
+      "loss": 1.6739,
+      "step": 35
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 1.05916166305542,
+      "learning_rate": 1.231578947368421e-05,
+      "loss": 1.7205,
+      "step": 40
+    },
+    {
+      "epoch": 0.4712041884816754,
+      "grad_norm": 1.1942501068115234,
+      "learning_rate": 1.3894736842105263e-05,
+      "loss": 1.7285,
+      "step": 45
+    },
+    {
+      "epoch": 0.5235602094240838,
+      "grad_norm": 1.3163442611694336,
+      "learning_rate": 1.547368421052632e-05,
+      "loss": 1.6304,
+      "step": 50
+    },
+    {
+      "epoch": 0.5759162303664922,
+      "grad_norm": 1.2255046367645264,
+      "learning_rate": 1.705263157894737e-05,
+      "loss": 1.6134,
+      "step": 55
+    },
+    {
+      "epoch": 0.6282722513089005,
+      "grad_norm": 1.4485703706741333,
+      "learning_rate": 1.8631578947368424e-05,
+      "loss": 1.5441,
+      "step": 60
+    },
+    {
+      "epoch": 0.680628272251309,
+      "grad_norm": 1.1530530452728271,
+      "learning_rate": 2.0210526315789475e-05,
+      "loss": 1.5696,
+      "step": 65
+    },
+    {
+      "epoch": 0.7329842931937173,
+      "grad_norm": 1.4592586755752563,
+      "learning_rate": 2.178947368421053e-05,
+      "loss": 1.4812,
+      "step": 70
+    },
+    {
+      "epoch": 0.7853403141361257,
+      "grad_norm": 1.124434471130371,
+      "learning_rate": 2.336842105263158e-05,
+      "loss": 1.4626,
+      "step": 75
+    },
+    {
+      "epoch": 0.837696335078534,
+      "grad_norm": 1.3748927116394043,
+      "learning_rate": 2.4947368421052635e-05,
+      "loss": 1.4415,
+      "step": 80
+    },
+    {
+      "epoch": 0.8900523560209425,
+      "grad_norm": 1.3555649518966675,
+      "learning_rate": 2.6526315789473685e-05,
+      "loss": 1.5086,
+      "step": 85
+    },
+    {
+      "epoch": 0.9424083769633508,
+      "grad_norm": 1.3602063655853271,
+      "learning_rate": 2.810526315789474e-05,
+      "loss": 1.4693,
+      "step": 90
+    },
+    {
+      "epoch": 0.9947643979057592,
+      "grad_norm": 1.361660122871399,
+      "learning_rate": 2.968421052631579e-05,
+      "loss": 1.3838,
+      "step": 95
+    },
+    {
+      "epoch": 1.0418848167539267,
+      "grad_norm": 1.7097163200378418,
+      "learning_rate": 2.999963648291697e-05,
+      "loss": 1.2911,
+      "step": 100
+    },
+    {
+      "epoch": 1.094240837696335,
+      "grad_norm": 1.4646059274673462,
+      "learning_rate": 2.999815972496425e-05,
+      "loss": 1.3181,
+      "step": 105
+    },
+    {
+      "epoch": 1.1465968586387434,
+      "grad_norm": 1.4632586240768433,
+      "learning_rate": 2.999554711807676e-05,
+      "loss": 1.2939,
+      "step": 110
+    },
+    {
+      "epoch": 1.1989528795811517,
+      "grad_norm": 1.604823350906372,
+      "learning_rate": 2.999179886011389e-05,
+      "loss": 1.2966,
+      "step": 115
+    },
+    {
+      "epoch": 1.2513089005235603,
+      "grad_norm": 1.2286367416381836,
+      "learning_rate": 2.998691523494079e-05,
+      "loss": 1.3602,
+      "step": 120
+    },
+    {
+      "epoch": 1.3036649214659686,
+      "grad_norm": 1.6536365747451782,
+      "learning_rate": 2.998089661240687e-05,
+      "loss": 1.2008,
+      "step": 125
+    },
+    {
+      "epoch": 1.356020942408377,
+      "grad_norm": 1.4944297075271606,
+      "learning_rate": 2.9973743448317773e-05,
+      "loss": 1.1954,
+      "step": 130
+    },
+    {
+      "epoch": 1.4083769633507854,
+      "grad_norm": 1.349837303161621,
+      "learning_rate": 2.9965456284400886e-05,
+      "loss": 1.2639,
+      "step": 135
+    },
+    {
+      "epoch": 1.4607329842931938,
+      "grad_norm": 1.2473978996276855,
+      "learning_rate": 2.99560357482643e-05,
+      "loss": 1.2141,
+      "step": 140
+    },
+    {
+      "epoch": 1.513089005235602,
+      "grad_norm": 1.4163920879364014,
+      "learning_rate": 2.9945482553349268e-05,
+      "loss": 1.2256,
+      "step": 145
+    },
+    {
+      "epoch": 1.5654450261780104,
+      "grad_norm": 1.323467493057251,
+      "learning_rate": 2.9933797498876185e-05,
+      "loss": 1.1521,
+      "step": 150
+    },
+    {
+      "epoch": 1.6178010471204187,
+      "grad_norm": 1.4941579103469849,
+      "learning_rate": 2.992098146978407e-05,
+      "loss": 1.1639,
+      "step": 155
+    },
+    {
+      "epoch": 1.6701570680628273,
+      "grad_norm": 1.607463002204895,
+      "learning_rate": 2.9907035436663535e-05,
+      "loss": 1.1055,
+      "step": 160
+    },
+    {
+      "epoch": 1.7225130890052356,
+      "grad_norm": 1.4040977954864502,
+      "learning_rate": 2.9891960455683273e-05,
+      "loss": 1.1411,
+      "step": 165
+    },
+    {
+      "epoch": 1.7748691099476441,
+      "grad_norm": 1.371125340461731,
+      "learning_rate": 2.9875757668510093e-05,
+      "loss": 1.0438,
+      "step": 170
+    },
+    {
+      "epoch": 1.8272251308900525,
+      "grad_norm": 1.4187743663787842,
+      "learning_rate": 2.9858428302222445e-05,
+      "loss": 1.036,
+      "step": 175
+    },
+    {
+      "epoch": 1.8795811518324608,
+      "grad_norm": 1.9025040864944458,
+      "learning_rate": 2.9839973669217484e-05,
+      "loss": 1.0829,
+      "step": 180
+    },
+    {
+      "epoch": 1.931937172774869,
+      "grad_norm": 2.0697097778320312,
+      "learning_rate": 2.9820395167111692e-05,
+      "loss": 1.0228,
+      "step": 185
+    },
+    {
+      "epoch": 1.9842931937172774,
+      "grad_norm": 1.448622465133667,
+      "learning_rate": 2.9799694278635034e-05,
+      "loss": 1.0084,
+      "step": 190
+    },
+    {
+      "epoch": 2.031413612565445,
+      "grad_norm": 1.621813416481018,
+      "learning_rate": 2.9777872571518657e-05,
+      "loss": 0.971,
+      "step": 195
+    },
+    {
+      "epoch": 2.0837696335078535,
+      "grad_norm": 1.6977280378341675,
+      "learning_rate": 2.9754931698376158e-05,
+      "loss": 0.9371,
+      "step": 200
+    },
+    {
+      "epoch": 2.136125654450262,
+      "grad_norm": 1.6247735023498535,
+      "learning_rate": 2.9730873396578444e-05,
+      "loss": 0.9774,
+      "step": 205
+    },
+    {
+      "epoch": 2.18848167539267,
+      "grad_norm": 1.7875080108642578,
+      "learning_rate": 2.970569948812214e-05,
+      "loss": 0.9071,
+      "step": 210
+    },
+    {
+      "epoch": 2.2408376963350785,
+      "grad_norm": 2.0753259658813477,
+      "learning_rate": 2.9679411879491622e-05,
+      "loss": 0.97,
+      "step": 215
+    },
+    {
+      "epoch": 2.2931937172774868,
+      "grad_norm": 1.5239359140396118,
+      "learning_rate": 2.965201256151462e-05,
+      "loss": 0.9081,
+      "step": 220
+    },
+    {
+      "epoch": 2.345549738219895,
+      "grad_norm": 1.6345692873001099,
+      "learning_rate": 2.962350360921145e-05,
+      "loss": 0.9176,
+      "step": 225
+    },
+    {
+      "epoch": 2.3979057591623034,
+      "grad_norm": 1.689063310623169,
+      "learning_rate": 2.959388718163786e-05,
+      "loss": 0.9204,
+      "step": 230
+    },
+    {
+      "epoch": 2.450261780104712,
+      "grad_norm": 1.674101710319519,
+      "learning_rate": 2.956316552172155e-05,
+      "loss": 0.902,
+      "step": 235
+    },
+    {
+      "epoch": 2.5026178010471205,
+      "grad_norm": 1.5287467241287231,
+      "learning_rate": 2.9531340956092274e-05,
+      "loss": 0.8586,
+      "step": 240
+    },
+    {
+      "epoch": 2.554973821989529,
+      "grad_norm": 2.18404221534729,
+      "learning_rate": 2.949841589490564e-05,
+      "loss": 0.8622,
+      "step": 245
+    },
+    {
+      "epoch": 2.607329842931937,
+      "grad_norm": 1.5042572021484375,
+      "learning_rate": 2.946439283166062e-05,
+      "loss": 0.8756,
+      "step": 250
+    },
+    {
+      "epoch": 2.6596858638743455,
+      "grad_norm": 2.0477566719055176,
+      "learning_rate": 2.9429274343010673e-05,
+      "loss": 0.8545,
+      "step": 255
+    },
+    {
+      "epoch": 2.712041884816754,
+      "grad_norm": 2.157820701599121,
+      "learning_rate": 2.939306308856862e-05,
+      "loss": 0.8528,
+      "step": 260
+    },
+    {
+      "epoch": 2.7643979057591626,
+      "grad_norm": 1.9966859817504883,
+      "learning_rate": 2.9355761810705226e-05,
+      "loss": 0.7391,
+      "step": 265
+    },
+    {
+      "epoch": 2.816753926701571,
+      "grad_norm": 1.804949164390564,
+      "learning_rate": 2.9317373334341517e-05,
+      "loss": 0.8296,
+      "step": 270
+    },
+    {
+      "epoch": 2.869109947643979,
+      "grad_norm": 1.699697494506836,
+      "learning_rate": 2.927790056673484e-05,
+      "loss": 0.7829,
+      "step": 275
+    },
+    {
+      "epoch": 2.9214659685863875,
+      "grad_norm": 1.8655725717544556,
+      "learning_rate": 2.923734649725867e-05,
+      "loss": 0.7538,
+      "step": 280
+    },
+    {
+      "epoch": 2.973821989528796,
+      "grad_norm": 1.4555854797363281,
+      "learning_rate": 2.9195714197176257e-05,
+      "loss": 0.7592,
+      "step": 285
+    },
+    {
+      "epoch": 3.020942408376963,
+      "grad_norm": 2.564462423324585,
+      "learning_rate": 2.915300681940799e-05,
+      "loss": 0.7199,
+      "step": 290
+    },
+    {
+      "epoch": 3.073298429319372,
+      "grad_norm": 1.9834420680999756,
+      "learning_rate": 2.9109227598292652e-05,
+      "loss": 0.6972,
+      "step": 295
+    },
+    {
+      "epoch": 3.1256544502617802,
+      "grad_norm": 1.7629621028900146,
+      "learning_rate": 2.9064379849342442e-05,
+      "loss": 0.6761,
+      "step": 300
+    },
+    {
+      "epoch": 3.1780104712041886,
+      "grad_norm": 2.1529428958892822,
+      "learning_rate": 2.9018466968991913e-05,
+      "loss": 0.6594,
+      "step": 305
+    },
+    {
+      "epoch": 3.230366492146597,
+      "grad_norm": 2.405747890472412,
+      "learning_rate": 2.8971492434340738e-05,
+      "loss": 0.6866,
+      "step": 310
+    },
+    {
+      "epoch": 3.282722513089005,
+      "grad_norm": 2.010468006134033,
+      "learning_rate": 2.8923459802890374e-05,
+      "loss": 0.7012,
+      "step": 315
+    },
+    {
+      "epoch": 3.3350785340314135,
+      "grad_norm": 2.1201961040496826,
+      "learning_rate": 2.8874372712274663e-05,
+      "loss": 0.6372,
+      "step": 320
+    },
+    {
+      "epoch": 3.387434554973822,
+      "grad_norm": 1.6618250608444214,
+      "learning_rate": 2.882423487998432e-05,
+      "loss": 0.6968,
+      "step": 325
+    },
+    {
+      "epoch": 3.4397905759162306,
+      "grad_norm": 2.3359334468841553,
+      "learning_rate": 2.877305010308541e-05,
+      "loss": 0.6412,
+      "step": 330
+    },
+    {
+      "epoch": 3.492146596858639,
+      "grad_norm": 2.0028185844421387,
+      "learning_rate": 2.8720822257931796e-05,
+      "loss": 0.689,
+      "step": 335
+    },
+    {
+      "epoch": 3.5445026178010473,
+      "grad_norm": 2.6226954460144043,
+      "learning_rate": 2.8667555299871564e-05,
+      "loss": 0.6438,
+      "step": 340
+    },
+    {
+      "epoch": 3.5968586387434556,
+      "grad_norm": 1.7858210802078247,
+      "learning_rate": 2.8613253262947457e-05,
+      "loss": 0.6228,
+      "step": 345
+    },
+    {
+      "epoch": 3.649214659685864,
+      "grad_norm": 1.8298466205596924,
+      "learning_rate": 2.8557920259591405e-05,
+      "loss": 0.5912,
+      "step": 350
+    },
+    {
+      "epoch": 3.701570680628272,
+      "grad_norm": 3.579176902770996,
+      "learning_rate": 2.850156048031304e-05,
+      "loss": 0.6164,
+      "step": 355
+    },
+    {
+      "epoch": 3.7539267015706805,
+      "grad_norm": 2.120554208755493,
+      "learning_rate": 2.8444178193382376e-05,
+      "loss": 0.6257,
+      "step": 360
+    },
+    {
+      "epoch": 3.806282722513089,
+      "grad_norm": 2.168713092803955,
+      "learning_rate": 2.8385777744506523e-05,
+      "loss": 0.598,
+      "step": 365
+    },
+    {
+      "epoch": 3.858638743455497,
+      "grad_norm": 1.5940132141113281,
+      "learning_rate": 2.83263635565006e-05,
+      "loss": 0.579,
+      "step": 370
+    },
+    {
+      "epoch": 3.9109947643979055,
+      "grad_norm": 2.5703248977661133,
+      "learning_rate": 2.82659401289528e-05,
+      "loss": 0.582,
+      "step": 375
+    },
+    {
+      "epoch": 3.9633507853403143,
+      "grad_norm": 2.092498779296875,
+      "learning_rate": 2.820451203788357e-05,
+      "loss": 0.5975,
+      "step": 380
+    },
+    {
+      "epoch": 4.010471204188482,
+      "grad_norm": 2.029618978500366,
+      "learning_rate": 2.814208393539911e-05,
+      "loss": 0.5906,
+      "step": 385
+    },
+    {
+      "epoch": 4.06282722513089,
+      "grad_norm": 2.290864944458008,
+      "learning_rate": 2.8078660549339047e-05,
+      "loss": 0.4818,
+      "step": 390
+    },
+    {
+      "epoch": 4.115183246073299,
+      "grad_norm": 1.9988826513290405,
+      "learning_rate": 2.8014246682918345e-05,
+      "loss": 0.5304,
+      "step": 395
+    },
+    {
+      "epoch": 4.167539267015707,
+      "grad_norm": 1.9701881408691406,
+      "learning_rate": 2.794884721436361e-05,
+      "loss": 0.5242,
+      "step": 400
+    },
+    {
+      "epoch": 4.219895287958115,
+      "grad_norm": 2.2701263427734375,
+      "learning_rate": 2.7882467096543585e-05,
+      "loss": 0.5123,
+      "step": 405
+    },
+    {
+      "epoch": 4.272251308900524,
+      "grad_norm": 2.2033908367156982,
+      "learning_rate": 2.781511135659411e-05,
+      "loss": 0.5038,
+      "step": 410
+    },
+    {
+      "epoch": 4.324607329842932,
+      "grad_norm": 2.103170394897461,
+      "learning_rate": 2.7746785095537357e-05,
+      "loss": 0.5031,
+      "step": 415
+    },
+    {
+      "epoch": 4.37696335078534,
+      "grad_norm": 2.2560765743255615,
+      "learning_rate": 2.7677493487895556e-05,
+      "loss": 0.5131,
+      "step": 420
+    },
+    {
+      "epoch": 4.429319371727749,
+      "grad_norm": 2.439460515975952,
+      "learning_rate": 2.76072417812991e-05,
+      "loss": 0.5047,
+      "step": 425
+    },
+    {
+      "epoch": 4.481675392670157,
+      "grad_norm": 1.9526431560516357,
+      "learning_rate": 2.7536035296089116e-05,
+      "loss": 0.4999,
+      "step": 430
+    },
+    {
+      "epoch": 4.534031413612565,
+      "grad_norm": 2.111056327819824,
+      "learning_rate": 2.746387942491456e-05,
+      "loss": 0.5154,
+      "step": 435
+    },
+    {
+      "epoch": 4.5863874345549736,
+      "grad_norm": 2.7262227535247803,
+      "learning_rate": 2.7390779632323815e-05,
+      "loss": 0.4889,
+      "step": 440
+    },
+    {
+      "epoch": 4.638743455497382,
+      "grad_norm": 2.0161452293395996,
+      "learning_rate": 2.7316741454350832e-05,
+      "loss": 0.4876,
+      "step": 445
+    },
+    {
+      "epoch": 4.69109947643979,
+      "grad_norm": 2.179011106491089,
+      "learning_rate": 2.7241770498095897e-05,
+      "loss": 0.4789,
+      "step": 450
+    },
+    {
+      "epoch": 4.7434554973821985,
+      "grad_norm": 2.0215184688568115,
+      "learning_rate": 2.7165872441300964e-05,
+      "loss": 0.4736,
+      "step": 455
+    },
+    {
+      "epoch": 4.795811518324607,
+      "grad_norm": 1.9461724758148193,
+      "learning_rate": 2.708905303191969e-05,
+      "loss": 0.4754,
+      "step": 460
+    },
+    {
+      "epoch": 4.848167539267016,
+      "grad_norm": 2.405299425125122,
+      "learning_rate": 2.7011318087682112e-05,
+      "loss": 0.4755,
+      "step": 465
+    },
+    {
+      "epoch": 4.900523560209424,
+      "grad_norm": 2.1616289615631104,
+      "learning_rate": 2.693267349565405e-05,
+      "loss": 0.4488,
+      "step": 470
+    },
+    {
+      "epoch": 4.952879581151833,
+      "grad_norm": 2.4113879203796387,
+      "learning_rate": 2.6853125211791292e-05,
+      "loss": 0.4203,
+      "step": 475
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.0132861137390137,
+      "learning_rate": 2.6772679260488504e-05,
+      "loss": 0.4389,
+      "step": 480
+    },
+    {
+      "epoch": 5.052356020942408,
+      "grad_norm": 2.1897664070129395,
+      "learning_rate": 2.6691341734122997e-05,
+      "loss": 0.4233,
+      "step": 485
+    },
+    {
+      "epoch": 5.104712041884817,
+      "grad_norm": 2.008359909057617,
+      "learning_rate": 2.660911879259335e-05,
+      "loss": 0.3524,
+      "step": 490
+    },
+    {
+      "epoch": 5.157068062827225,
+      "grad_norm": 2.1782288551330566,
+      "learning_rate": 2.6526016662852887e-05,
+      "loss": 0.3928,
+      "step": 495
+    },
+    {
+      "epoch": 5.209424083769633,
+      "grad_norm": 2.0432088375091553,
+      "learning_rate": 2.6442041638438098e-05,
+      "loss": 0.3928,
+      "step": 500
+    },
+    {
+      "epoch": 5.261780104712042,
+      "grad_norm": 2.686347723007202,
+      "learning_rate": 2.635720007899201e-05,
+      "loss": 0.388,
+      "step": 505
+    },
+    {
+      "epoch": 5.31413612565445,
+      "grad_norm": 2.0326364040374756,
+      "learning_rate": 2.6271498409782582e-05,
+      "loss": 0.3846,
+      "step": 510
+    },
+    {
+      "epoch": 5.366492146596858,
+      "grad_norm": 1.9769495725631714,
+      "learning_rate": 2.6184943121216058e-05,
+      "loss": 0.3545,
+      "step": 515
+    },
+    {
+      "epoch": 5.418848167539267,
+      "grad_norm": 2.249706268310547,
+      "learning_rate": 2.6097540768345472e-05,
+      "loss": 0.3698,
+      "step": 520
+    },
+    {
+      "epoch": 5.471204188481676,
+      "grad_norm": 1.8810491561889648,
+      "learning_rate": 2.600929797037419e-05,
+      "loss": 0.4005,
+      "step": 525
+    },
+    {
+      "epoch": 5.523560209424084,
+      "grad_norm": 2.422290802001953,
+      "learning_rate": 2.592022141015464e-05,
+      "loss": 0.3855,
+      "step": 530
+    },
+    {
+      "epoch": 5.575916230366492,
+      "grad_norm": 2.183039665222168,
+      "learning_rate": 2.5830317833682186e-05,
+      "loss": 0.354,
+      "step": 535
+    },
+    {
+      "epoch": 5.628272251308901,
+      "grad_norm": 1.920445203781128,
+      "learning_rate": 2.5739594049584255e-05,
+      "loss": 0.3601,
+      "step": 540
+    },
+    {
+      "epoch": 5.680628272251309,
+      "grad_norm": 2.186728000640869,
+      "learning_rate": 2.5648056928604682e-05,
+      "loss": 0.3806,
+      "step": 545
+    },
+    {
+      "epoch": 5.732984293193717,
+      "grad_norm": 2.2915523052215576,
+      "learning_rate": 2.5555713403083385e-05,
+      "loss": 0.3591,
+      "step": 550
+    },
+    {
+      "epoch": 5.785340314136126,
+      "grad_norm": 2.1855974197387695,
+      "learning_rate": 2.546257046643136e-05,
+      "loss": 0.377,
+      "step": 555
+    },
+    {
+      "epoch": 5.837696335078534,
+      "grad_norm": 2.0636916160583496,
+      "learning_rate": 2.536863517260104e-05,
+      "loss": 0.3678,
+      "step": 560
+    },
+    {
+      "epoch": 5.890052356020942,
+      "grad_norm": 2.7312142848968506,
+      "learning_rate": 2.52739146355521e-05,
+      "loss": 0.3922,
+      "step": 565
+    },
+    {
+      "epoch": 5.942408376963351,
+      "grad_norm": 1.9910225868225098,
+      "learning_rate": 2.5178416028712692e-05,
+      "loss": 0.3741,
+      "step": 570
+    },
+    {
+      "epoch": 5.994764397905759,
+      "grad_norm": 2.068664312362671,
+      "learning_rate": 2.5082146584436166e-05,
+      "loss": 0.3749,
+      "step": 575
+    },
+    {
+      "epoch": 6.041884816753926,
+      "grad_norm": 2.0572855472564697,
+      "learning_rate": 2.4985113593453365e-05,
+      "loss": 0.2834,
+      "step": 580
+    },
+    {
+      "epoch": 6.0942408376963355,
+      "grad_norm": 2.303874969482422,
+      "learning_rate": 2.488732440432049e-05,
+      "loss": 0.2875,
+      "step": 585
+    },
+    {
+      "epoch": 6.146596858638744,
+      "grad_norm": 2.420100212097168,
+      "learning_rate": 2.478878642286253e-05,
+      "loss": 0.2938,
+      "step": 590
+    },
+    {
+      "epoch": 6.198952879581152,
+      "grad_norm": 1.8585245609283447,
+      "learning_rate": 2.4689507111612455e-05,
+      "loss": 0.299,
+      "step": 595
+    },
+    {
+      "epoch": 6.2513089005235605,
+      "grad_norm": 2.8291428089141846,
+      "learning_rate": 2.458949398924601e-05,
+      "loss": 0.2928,
+      "step": 600
+    },
+    {
+      "epoch": 6.303664921465969,
+      "grad_norm": 1.6938339471817017,
+      "learning_rate": 2.448875463001236e-05,
+      "loss": 0.2984,
+      "step": 605
+    },
+    {
+      "epoch": 6.356020942408377,
+      "grad_norm": 2.571981191635132,
+      "learning_rate": 2.438729666316041e-05,
+      "loss": 0.3253,
+      "step": 610
+    },
+    {
+      "epoch": 6.408376963350785,
+      "grad_norm": 2.0141608715057373,
+      "learning_rate": 2.4285127772361077e-05,
+      "loss": 0.2898,
+      "step": 615
+    },
+    {
+      "epoch": 6.460732984293194,
+      "grad_norm": 2.1542282104492188,
+      "learning_rate": 2.4182255695125344e-05,
+      "loss": 0.3346,
+      "step": 620
+    },
+    {
+      "epoch": 6.513089005235602,
+      "grad_norm": 2.03896164894104,
+      "learning_rate": 2.407868822221833e-05,
+      "loss": 0.3246,
+      "step": 625
+    },
+    {
+      "epoch": 6.56544502617801,
+      "grad_norm": 2.094012975692749,
+      "learning_rate": 2.3974433197069207e-05,
+      "loss": 0.3111,
+      "step": 630
+    },
+    {
+      "epoch": 6.617801047120419,
+      "grad_norm": 2.2046549320220947,
+      "learning_rate": 2.386949851517726e-05,
+      "loss": 0.2865,
+      "step": 635
+    },
+    {
+      "epoch": 6.670157068062827,
+      "grad_norm": 2.1831257343292236,
+      "learning_rate": 2.376389212351391e-05,
+      "loss": 0.3207,
+      "step": 640
+    },
+    {
+      "epoch": 6.722513089005235,
+      "grad_norm": 1.9105017185211182,
+      "learning_rate": 2.3657622019920865e-05,
+      "loss": 0.3207,
+      "step": 645
+    },
+    {
+      "epoch": 6.774869109947644,
+      "grad_norm": 2.251492738723755,
+      "learning_rate": 2.3550696252504435e-05,
+      "loss": 0.3073,
+      "step": 650
+    },
+    {
+      "epoch": 6.827225130890052,
+      "grad_norm": 2.173784017562866,
+      "learning_rate": 2.3443122919026034e-05,
+      "loss": 0.3105,
+      "step": 655
+    },
+    {
+      "epoch": 6.879581151832461,
+      "grad_norm": 2.0459015369415283,
+      "learning_rate": 2.3334910166288898e-05,
+      "loss": 0.3132,
+      "step": 660
+    },
+    {
+      "epoch": 6.9319371727748695,
+      "grad_norm": 2.2690305709838867,
+      "learning_rate": 2.3226066189521123e-05,
+      "loss": 0.2815,
+      "step": 665
+    },
+    {
+      "epoch": 6.984293193717278,
+      "grad_norm": 1.8328899145126343,
+      "learning_rate": 2.3116599231755017e-05,
+      "loss": 0.2743,
+      "step": 670
+    },
+    {
+      "epoch": 7.031413612565445,
+      "grad_norm": 1.8480794429779053,
+      "learning_rate": 2.3006517583202808e-05,
+      "loss": 0.2538,
+      "step": 675
+    },
+    {
+      "epoch": 7.0837696335078535,
+      "grad_norm": 1.5677030086517334,
+      "learning_rate": 2.289582958062885e-05,
+      "loss": 0.2663,
+      "step": 680
+    },
+    {
+      "epoch": 7.136125654450262,
+      "grad_norm": 1.777860164642334,
+      "learning_rate": 2.2784543606718227e-05,
+      "loss": 0.2417,
+      "step": 685
+    },
+    {
+      "epoch": 7.18848167539267,
+      "grad_norm": 2.3644204139709473,
+      "learning_rate": 2.267266808944192e-05,
+      "loss": 0.2598,
+      "step": 690
+    },
+    {
+      "epoch": 7.2408376963350785,
+      "grad_norm": 1.845493197441101,
+      "learning_rate": 2.2560211501418525e-05,
+      "loss": 0.2524,
+      "step": 695
+    },
+    {
+      "epoch": 7.293193717277487,
+      "grad_norm": 2.1028873920440674,
+      "learning_rate": 2.2447182359272635e-05,
+      "loss": 0.2325,
+      "step": 700
+    },
+    {
+      "epoch": 7.345549738219895,
+      "grad_norm": 2.070425033569336,
+      "learning_rate": 2.2333589222989798e-05,
+      "loss": 0.2503,
+      "step": 705
+    },
+    {
+      "epoch": 7.397905759162303,
+      "grad_norm": 2.3109984397888184,
+      "learning_rate": 2.2219440695268294e-05,
+      "loss": 0.2597,
+      "step": 710
+    },
+    {
+      "epoch": 7.450261780104712,
+      "grad_norm": 2.202803134918213,
+      "learning_rate": 2.2104745420867624e-05,
+      "loss": 0.2347,
+      "step": 715
+    },
+    {
+      "epoch": 7.50261780104712,
+      "grad_norm": 1.9535624980926514,
+      "learning_rate": 2.1989512085953793e-05,
+      "loss": 0.2584,
+      "step": 720
+    },
+    {
+      "epoch": 7.554973821989529,
+      "grad_norm": 2.0640347003936768,
+      "learning_rate": 2.18737494174415e-05,
+      "loss": 0.2595,
+      "step": 725
+    },
+    {
+      "epoch": 7.607329842931938,
+      "grad_norm": 1.6874743700027466,
+      "learning_rate": 2.1757466182333254e-05,
+      "loss": 0.2544,
+      "step": 730
+    },
+    {
+      "epoch": 7.659685863874346,
+      "grad_norm": 1.7148810625076294,
+      "learning_rate": 2.1640671187055383e-05,
+      "loss": 0.258,
+      "step": 735
+    },
+    {
+      "epoch": 7.712041884816754,
+      "grad_norm": 1.8402714729309082,
+      "learning_rate": 2.152337327679112e-05,
+      "loss": 0.2581,
+      "step": 740
+    },
+    {
+      "epoch": 7.7643979057591626,
+      "grad_norm": 2.2578415870666504,
+      "learning_rate": 2.140558133481074e-05,
+      "loss": 0.2474,
+      "step": 745
+    },
+    {
+      "epoch": 7.816753926701571,
+      "grad_norm": 1.9558266401290894,
+      "learning_rate": 2.1287304281798794e-05,
+      "loss": 0.2247,
+      "step": 750
+    },
+    {
+      "epoch": 7.869109947643979,
+      "grad_norm": 2.2188961505889893,
+      "learning_rate": 2.1168551075178543e-05,
+      "loss": 0.2303,
+      "step": 755
+    },
+    {
+      "epoch": 7.9214659685863875,
+      "grad_norm": 1.9665825366973877,
+      "learning_rate": 2.1049330708433563e-05,
+      "loss": 0.2477,
+      "step": 760
+    },
+    {
+      "epoch": 7.973821989528796,
+      "grad_norm": 2.1581296920776367,
+      "learning_rate": 2.0929652210426663e-05,
+      "loss": 0.2244,
+      "step": 765
+    },
+    {
+      "epoch": 8.020942408376964,
+      "grad_norm": 2.0662615299224854,
+      "learning_rate": 2.0809524644716106e-05,
+      "loss": 0.2146,
+      "step": 770
+    },
+    {
+      "epoch": 8.073298429319372,
+      "grad_norm": 2.4462475776672363,
+      "learning_rate": 2.0688957108869203e-05,
+      "loss": 0.2059,
+      "step": 775
+    },
+    {
+      "epoch": 8.12565445026178,
+      "grad_norm": 1.8161300420761108,
+      "learning_rate": 2.056795873377331e-05,
+      "loss": 0.218,
+      "step": 780
+    },
+    {
+      "epoch": 8.178010471204189,
+      "grad_norm": 1.6970865726470947,
+      "learning_rate": 2.044653868294436e-05,
+      "loss": 0.2058,
+      "step": 785
+    },
+    {
+      "epoch": 8.230366492146597,
+      "grad_norm": 2.00407075881958,
+      "learning_rate": 2.0324706151832853e-05,
+      "loss": 0.2195,
+      "step": 790
+    },
+    {
+      "epoch": 8.282722513089006,
+      "grad_norm": 2.514988899230957,
+      "learning_rate": 2.0202470367127477e-05,
+      "loss": 0.2239,
+      "step": 795
+    },
+    {
+      "epoch": 8.335078534031414,
+      "grad_norm": 2.4687931537628174,
+      "learning_rate": 2.0079840586056343e-05,
+      "loss": 0.1918,
+      "step": 800
+    },
+    {
+      "epoch": 8.387434554973822,
+      "grad_norm": 1.8812583684921265,
+      "learning_rate": 1.9956826095685917e-05,
+      "loss": 0.2086,
+      "step": 805
+    },
+    {
+      "epoch": 8.43979057591623,
+      "grad_norm": 1.6383140087127686,
+      "learning_rate": 1.9833436212217682e-05,
+      "loss": 0.2052,
+      "step": 810
+    },
+    {
+      "epoch": 8.492146596858639,
+      "grad_norm": 2.128833055496216,
+      "learning_rate": 1.9709680280282593e-05,
+      "loss": 0.2187,
+      "step": 815
+    },
+    {
+      "epoch": 8.544502617801047,
+      "grad_norm": 1.8959410190582275,
+      "learning_rate": 1.9585567672233398e-05,
+      "loss": 0.2092,
+      "step": 820
+    },
+    {
+      "epoch": 8.596858638743456,
+      "grad_norm": 1.8595294952392578,
+      "learning_rate": 1.9461107787434833e-05,
+      "loss": 0.1996,
+      "step": 825
+    },
+    {
+      "epoch": 8.649214659685864,
+      "grad_norm": 1.96145498752594,
+      "learning_rate": 1.9336310051551788e-05,
+      "loss": 0.217,
+      "step": 830
+    },
+    {
+      "epoch": 8.701570680628272,
+      "grad_norm": 1.8644137382507324,
+      "learning_rate": 1.9211183915835492e-05,
+      "loss": 0.2105,
+      "step": 835
+    },
+    {
+      "epoch": 8.75392670157068,
+      "grad_norm": 2.339465618133545,
+      "learning_rate": 1.9085738856407708e-05,
+      "loss": 0.211,
+      "step": 840
+    },
+    {
+      "epoch": 8.806282722513089,
+      "grad_norm": 1.9026511907577515,
+      "learning_rate": 1.895998437354312e-05,
+      "loss": 0.2338,
+      "step": 845
+    },
+    {
+      "epoch": 8.858638743455497,
+      "grad_norm": 2.136833906173706,
+      "learning_rate": 1.883392999094984e-05,
+      "loss": 0.2332,
+      "step": 850
+    },
+    {
+      "epoch": 8.910994764397905,
+      "grad_norm": 2.0453922748565674,
+      "learning_rate": 1.8707585255048152e-05,
+      "loss": 0.1852,
+      "step": 855
+    },
+    {
+      "epoch": 8.963350785340314,
+      "grad_norm": 2.331050157546997,
+      "learning_rate": 1.8580959734247537e-05,
+      "loss": 0.193,
+      "step": 860
+    },
+    {
+      "epoch": 9.010471204188482,
+      "grad_norm": 2.5257890224456787,
+      "learning_rate": 1.8454063018222022e-05,
+      "loss": 0.2143,
+      "step": 865
+    },
+    {
+      "epoch": 9.06282722513089,
+      "grad_norm": 1.800729751586914,
+      "learning_rate": 1.832690471718397e-05,
+      "loss": 0.1547,
+      "step": 870
+    },
+    {
+      "epoch": 9.115183246073299,
+      "grad_norm": 1.547395944595337,
+      "learning_rate": 1.8199494461156203e-05,
+      "loss": 0.1806,
+      "step": 875
+    },
+    {
+      "epoch": 9.167539267015707,
+      "grad_norm": 1.5873461961746216,
+      "learning_rate": 1.8071841899242775e-05,
+      "loss": 0.1745,
+      "step": 880
+    },
+    {
+      "epoch": 9.219895287958115,
+      "grad_norm": 1.8685342073440552,
+      "learning_rate": 1.7943956698898167e-05,
+      "loss": 0.1788,
+      "step": 885
+    },
+    {
+      "epoch": 9.272251308900524,
+      "grad_norm": 2.1903324127197266,
+      "learning_rate": 1.781584854519516e-05,
+      "loss": 0.1856,
+      "step": 890
+    },
+    {
+      "epoch": 9.324607329842932,
+      "grad_norm": 1.6244503259658813,
+      "learning_rate": 1.7687527140091365e-05,
+      "loss": 0.1702,
+      "step": 895
+    },
+    {
+      "epoch": 9.37696335078534,
+      "grad_norm": 2.138651132583618,
+      "learning_rate": 1.755900220169448e-05,
+      "loss": 0.1927,
+      "step": 900
+    },
+    {
+      "epoch": 9.429319371727749,
+      "grad_norm": 1.89018976688385,
+      "learning_rate": 1.743028346352627e-05,
+      "loss": 0.1828,
+      "step": 905
+    },
+    {
+      "epoch": 9.481675392670157,
+      "grad_norm": 1.7095950841903687,
+      "learning_rate": 1.7301380673785486e-05,
+      "loss": 0.192,
+      "step": 910
+    },
+    {
+      "epoch": 9.534031413612565,
+      "grad_norm": 2.298391103744507,
+      "learning_rate": 1.7172303594609543e-05,
+      "loss": 0.1727,
+      "step": 915
+    },
+    {
+      "epoch": 9.586387434554974,
+      "grad_norm": 2.142773389816284,
+      "learning_rate": 1.704306200133526e-05,
+      "loss": 0.1825,
+      "step": 920
+    },
+    {
+      "epoch": 9.638743455497382,
+      "grad_norm": 1.678457498550415,
+      "learning_rate": 1.6913665681758518e-05,
+      "loss": 0.1866,
+      "step": 925
+    },
+    {
+      "epoch": 9.69109947643979,
+      "grad_norm": 1.5535097122192383,
+      "learning_rate": 1.6784124435393034e-05,
+      "loss": 0.1916,
+      "step": 930
+    },
+    {
+      "epoch": 9.743455497382199,
+      "grad_norm": 1.5964089632034302,
+      "learning_rate": 1.6654448072728165e-05,
+      "loss": 0.1726,
+      "step": 935
+    },
+    {
+      "epoch": 9.795811518324607,
+      "grad_norm": 2.015465497970581,
+      "learning_rate": 1.652464641448601e-05,
+      "loss": 0.1914,
+      "step": 940
+    },
+    {
+      "epoch": 9.848167539267015,
+      "grad_norm": 2.025540351867676,
+      "learning_rate": 1.6394729290877606e-05,
+      "loss": 0.1784,
+      "step": 945
+    },
+    {
+      "epoch": 9.900523560209423,
+      "grad_norm": 1.693466067314148,
+      "learning_rate": 1.6264706540858465e-05,
+      "loss": 0.1731,
+      "step": 950
+    },
+    {
+      "epoch": 9.952879581151832,
+      "grad_norm": 2.2833855152130127,
+      "learning_rate": 1.6134588011383472e-05,
+      "loss": 0.2008,
+      "step": 955
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.3272955417633057,
+      "learning_rate": 1.600438355666113e-05,
+      "loss": 0.1861,
+      "step": 960
+    },
+    {
+      "epoch": 10.052356020942408,
+      "grad_norm": 1.6399215459823608,
+      "learning_rate": 1.5874103037407288e-05,
+      "loss": 0.159,
+      "step": 965
+    },
+    {
+      "epoch": 10.104712041884817,
+      "grad_norm": 1.7252026796340942,
+      "learning_rate": 1.5743756320098334e-05,
+      "loss": 0.166,
+      "step": 970
+    },
+    {
+      "epoch": 10.157068062827225,
+      "grad_norm": 1.4673538208007812,
+      "learning_rate": 1.5613353276224034e-05,
+      "loss": 0.1595,
+      "step": 975
+    },
+    {
+      "epoch": 10.209424083769633,
+      "grad_norm": 1.8614445924758911,
+      "learning_rate": 1.5482903781539887e-05,
+      "loss": 0.1635,
+      "step": 980
+    },
+    {
+      "epoch": 10.261780104712042,
+      "grad_norm": 1.6224993467330933,
+      "learning_rate": 1.5352417715319235e-05,
+      "loss": 0.157,
+      "step": 985
+    },
+    {
+      "epoch": 10.31413612565445,
+      "grad_norm": 1.548218846321106,
+      "learning_rate": 1.5221904959605081e-05,
+      "loss": 0.1755,
+      "step": 990
+    },
+    {
+      "epoch": 10.366492146596858,
+      "grad_norm": 1.4170892238616943,
+      "learning_rate": 1.509137539846169e-05,
+      "loss": 0.1556,
+      "step": 995
+    },
+    {
+      "epoch": 10.418848167539267,
+      "grad_norm": 1.7958966493606567,
+      "learning_rate": 1.4960838917226034e-05,
+      "loss": 0.1658,
+      "step": 1000
+    },
+    {
+      "epoch": 10.471204188481675,
+      "grad_norm": 1.8197486400604248,
+      "learning_rate": 1.483030540175918e-05,
+      "loss": 0.1634,
+      "step": 1005
+    },
+    {
+      "epoch": 10.523560209424083,
+      "grad_norm": 1.8356825113296509,
+      "learning_rate": 1.4699784737697583e-05,
+      "loss": 0.1673,
+      "step": 1010
+    },
+    {
+      "epoch": 10.575916230366492,
+      "grad_norm": 1.7088730335235596,
+      "learning_rate": 1.4569286809704406e-05,
+      "loss": 0.1643,
+      "step": 1015
+    },
+    {
+      "epoch": 10.6282722513089,
+      "grad_norm": 1.756155252456665,
+      "learning_rate": 1.4438821500720998e-05,
+      "loss": 0.1644,
+      "step": 1020
+    },
+    {
+      "epoch": 10.680628272251308,
+      "grad_norm": 1.9680912494659424,
+      "learning_rate": 1.4308398691218341e-05,
+      "loss": 0.1625,
+      "step": 1025
+    },
+    {
+      "epoch": 10.732984293193716,
+      "grad_norm": 1.5771136283874512,
+      "learning_rate": 1.417802825844885e-05,
+      "loss": 0.1751,
+      "step": 1030
+    },
+    {
+      "epoch": 10.785340314136125,
+      "grad_norm": 1.76025390625,
+      "learning_rate": 1.4047720075698302e-05,
+      "loss": 0.164,
+      "step": 1035
+    },
+    {
+      "epoch": 10.837696335078533,
+      "grad_norm": 2.363912343978882,
+      "learning_rate": 1.3917484011538135e-05,
+      "loss": 0.1554,
+      "step": 1040
+    },
+    {
+      "epoch": 10.890052356020943,
+      "grad_norm": 1.7519829273223877,
+      "learning_rate": 1.378732992907805e-05,
+      "loss": 0.1676,
+      "step": 1045
+    },
+    {
+      "epoch": 10.942408376963352,
+      "grad_norm": 1.434294581413269,
+      "learning_rate": 1.3657267685219072e-05,
+      "loss": 0.1353,
+      "step": 1050
+    },
+    {
+      "epoch": 10.99476439790576,
+      "grad_norm": 1.4985880851745605,
+      "learning_rate": 1.3527307129907049e-05,
+      "loss": 0.1487,
+      "step": 1055
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.0022214797072794e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70bca501007d7886eed27b5fce908bf9eeef36b2f006f1a19cae3b7227bd0b5
+size 7608

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1056/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af6cfca4b3313f75ea2f09909f080f79068f587098acedc6c5d9652be958920
+size 1342239008

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/latest

@@ -0,0 +1 @@
+global_step1146

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44d342be857c492dd21543be91be6142ccf23395d4a1fa190d12088d7db0edb0
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c916994bdbc9136797c4127aa4befb8f5ffb22908a3bef25987c345f78d33f30
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24cddddcd3ff905679775cee1413d60d5dee0f7bd76f58a25cc198bd68a880f8
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19a06aacb769342dd983cc874b5730abef40cf1830b1f05bc791b4273890b70e
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28fe80b42d95cf177ce05604b30fc9512e33cb9b4b2f3ac90b908861d562da42
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64269b328adba235018d730b00b3623014b875bd5851dea0d78cbd20628685dd
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20b1ca5d5ea6a0f85b0bf02d857312dd6e8be1b8cd4c7f8af73ea76cac5bd7b6
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79fe7363783a2345830276e2618ae371b8c3232baa1d95190e83f6ee5c1d96e8
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1bfc7a9e74f1fa067ed8960bbee8994b0f5ecd2818404c7d5166a2ff0eff0d
+size 1064

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|end_of_text|>"
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/tokenizer_config.json

@@ -0,0 +1,2063 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
+  "tokenizer_class": "PreTrainedTokenizer"
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/trainer_state.json

@@ -0,0 +1,1644 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.0,
+  "eval_steps": 500,
+  "global_step": 1152,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05235602094240838,
+      "grad_norm": 1.479238510131836,
+      "learning_rate": 1.2631578947368422e-06,
+      "loss": 1.859,
+      "step": 5
+    },
+    {
+      "epoch": 0.10471204188481675,
+      "grad_norm": 1.949265480041504,
+      "learning_rate": 2.842105263157895e-06,
+      "loss": 1.8637,
+      "step": 10
+    },
+    {
+      "epoch": 0.15706806282722513,
+      "grad_norm": 1.8027445077896118,
+      "learning_rate": 4.421052631578947e-06,
+      "loss": 1.8695,
+      "step": 15
+    },
+    {
+      "epoch": 0.2094240837696335,
+      "grad_norm": 1.3422410488128662,
+      "learning_rate": 6e-06,
+      "loss": 1.7703,
+      "step": 20
+    },
+    {
+      "epoch": 0.2617801047120419,
+      "grad_norm": 1.3363796472549438,
+      "learning_rate": 7.578947368421053e-06,
+      "loss": 1.7696,
+      "step": 25
+    },
+    {
+      "epoch": 0.31413612565445026,
+      "grad_norm": 1.1196855306625366,
+      "learning_rate": 9.157894736842105e-06,
+      "loss": 1.748,
+      "step": 30
+    },
+    {
+      "epoch": 0.36649214659685864,
+      "grad_norm": 1.0649173259735107,
+      "learning_rate": 1.0736842105263158e-05,
+      "loss": 1.6739,
+      "step": 35
+    },
+    {
+      "epoch": 0.418848167539267,
+      "grad_norm": 1.05916166305542,
+      "learning_rate": 1.231578947368421e-05,
+      "loss": 1.7205,
+      "step": 40
+    },
+    {
+      "epoch": 0.4712041884816754,
+      "grad_norm": 1.1942501068115234,
+      "learning_rate": 1.3894736842105263e-05,
+      "loss": 1.7285,
+      "step": 45
+    },
+    {
+      "epoch": 0.5235602094240838,
+      "grad_norm": 1.3163442611694336,
+      "learning_rate": 1.547368421052632e-05,
+      "loss": 1.6304,
+      "step": 50
+    },
+    {
+      "epoch": 0.5759162303664922,
+      "grad_norm": 1.2255046367645264,
+      "learning_rate": 1.705263157894737e-05,
+      "loss": 1.6134,
+      "step": 55
+    },
+    {
+      "epoch": 0.6282722513089005,
+      "grad_norm": 1.4485703706741333,
+      "learning_rate": 1.8631578947368424e-05,
+      "loss": 1.5441,
+      "step": 60
+    },
+    {
+      "epoch": 0.680628272251309,
+      "grad_norm": 1.1530530452728271,
+      "learning_rate": 2.0210526315789475e-05,
+      "loss": 1.5696,
+      "step": 65
+    },
+    {
+      "epoch": 0.7329842931937173,
+      "grad_norm": 1.4592586755752563,
+      "learning_rate": 2.178947368421053e-05,
+      "loss": 1.4812,
+      "step": 70
+    },
+    {
+      "epoch": 0.7853403141361257,
+      "grad_norm": 1.124434471130371,
+      "learning_rate": 2.336842105263158e-05,
+      "loss": 1.4626,
+      "step": 75
+    },
+    {
+      "epoch": 0.837696335078534,
+      "grad_norm": 1.3748927116394043,
+      "learning_rate": 2.4947368421052635e-05,
+      "loss": 1.4415,
+      "step": 80
+    },
+    {
+      "epoch": 0.8900523560209425,
+      "grad_norm": 1.3555649518966675,
+      "learning_rate": 2.6526315789473685e-05,
+      "loss": 1.5086,
+      "step": 85
+    },
+    {
+      "epoch": 0.9424083769633508,
+      "grad_norm": 1.3602063655853271,
+      "learning_rate": 2.810526315789474e-05,
+      "loss": 1.4693,
+      "step": 90
+    },
+    {
+      "epoch": 0.9947643979057592,
+      "grad_norm": 1.361660122871399,
+      "learning_rate": 2.968421052631579e-05,
+      "loss": 1.3838,
+      "step": 95
+    },
+    {
+      "epoch": 1.0418848167539267,
+      "grad_norm": 1.7097163200378418,
+      "learning_rate": 2.999963648291697e-05,
+      "loss": 1.2911,
+      "step": 100
+    },
+    {
+      "epoch": 1.094240837696335,
+      "grad_norm": 1.4646059274673462,
+      "learning_rate": 2.999815972496425e-05,
+      "loss": 1.3181,
+      "step": 105
+    },
+    {
+      "epoch": 1.1465968586387434,
+      "grad_norm": 1.4632586240768433,
+      "learning_rate": 2.999554711807676e-05,
+      "loss": 1.2939,
+      "step": 110
+    },
+    {
+      "epoch": 1.1989528795811517,
+      "grad_norm": 1.604823350906372,
+      "learning_rate": 2.999179886011389e-05,
+      "loss": 1.2966,
+      "step": 115
+    },
+    {
+      "epoch": 1.2513089005235603,
+      "grad_norm": 1.2286367416381836,
+      "learning_rate": 2.998691523494079e-05,
+      "loss": 1.3602,
+      "step": 120
+    },
+    {
+      "epoch": 1.3036649214659686,
+      "grad_norm": 1.6536365747451782,
+      "learning_rate": 2.998089661240687e-05,
+      "loss": 1.2008,
+      "step": 125
+    },
+    {
+      "epoch": 1.356020942408377,
+      "grad_norm": 1.4944297075271606,
+      "learning_rate": 2.9973743448317773e-05,
+      "loss": 1.1954,
+      "step": 130
+    },
+    {
+      "epoch": 1.4083769633507854,
+      "grad_norm": 1.349837303161621,
+      "learning_rate": 2.9965456284400886e-05,
+      "loss": 1.2639,
+      "step": 135
+    },
+    {
+      "epoch": 1.4607329842931938,
+      "grad_norm": 1.2473978996276855,
+      "learning_rate": 2.99560357482643e-05,
+      "loss": 1.2141,
+      "step": 140
+    },
+    {
+      "epoch": 1.513089005235602,
+      "grad_norm": 1.4163920879364014,
+      "learning_rate": 2.9945482553349268e-05,
+      "loss": 1.2256,
+      "step": 145
+    },
+    {
+      "epoch": 1.5654450261780104,
+      "grad_norm": 1.323467493057251,
+      "learning_rate": 2.9933797498876185e-05,
+      "loss": 1.1521,
+      "step": 150
+    },
+    {
+      "epoch": 1.6178010471204187,
+      "grad_norm": 1.4941579103469849,
+      "learning_rate": 2.992098146978407e-05,
+      "loss": 1.1639,
+      "step": 155
+    },
+    {
+      "epoch": 1.6701570680628273,
+      "grad_norm": 1.607463002204895,
+      "learning_rate": 2.9907035436663535e-05,
+      "loss": 1.1055,
+      "step": 160
+    },
+    {
+      "epoch": 1.7225130890052356,
+      "grad_norm": 1.4040977954864502,
+      "learning_rate": 2.9891960455683273e-05,
+      "loss": 1.1411,
+      "step": 165
+    },
+    {
+      "epoch": 1.7748691099476441,
+      "grad_norm": 1.371125340461731,
+      "learning_rate": 2.9875757668510093e-05,
+      "loss": 1.0438,
+      "step": 170
+    },
+    {
+      "epoch": 1.8272251308900525,
+      "grad_norm": 1.4187743663787842,
+      "learning_rate": 2.9858428302222445e-05,
+      "loss": 1.036,
+      "step": 175
+    },
+    {
+      "epoch": 1.8795811518324608,
+      "grad_norm": 1.9025040864944458,
+      "learning_rate": 2.9839973669217484e-05,
+      "loss": 1.0829,
+      "step": 180
+    },
+    {
+      "epoch": 1.931937172774869,
+      "grad_norm": 2.0697097778320312,
+      "learning_rate": 2.9820395167111692e-05,
+      "loss": 1.0228,
+      "step": 185
+    },
+    {
+      "epoch": 1.9842931937172774,
+      "grad_norm": 1.448622465133667,
+      "learning_rate": 2.9799694278635034e-05,
+      "loss": 1.0084,
+      "step": 190
+    },
+    {
+      "epoch": 2.031413612565445,
+      "grad_norm": 1.621813416481018,
+      "learning_rate": 2.9777872571518657e-05,
+      "loss": 0.971,
+      "step": 195
+    },
+    {
+      "epoch": 2.0837696335078535,
+      "grad_norm": 1.6977280378341675,
+      "learning_rate": 2.9754931698376158e-05,
+      "loss": 0.9371,
+      "step": 200
+    },
+    {
+      "epoch": 2.136125654450262,
+      "grad_norm": 1.6247735023498535,
+      "learning_rate": 2.9730873396578444e-05,
+      "loss": 0.9774,
+      "step": 205
+    },
+    {
+      "epoch": 2.18848167539267,
+      "grad_norm": 1.7875080108642578,
+      "learning_rate": 2.970569948812214e-05,
+      "loss": 0.9071,
+      "step": 210
+    },
+    {
+      "epoch": 2.2408376963350785,
+      "grad_norm": 2.0753259658813477,
+      "learning_rate": 2.9679411879491622e-05,
+      "loss": 0.97,
+      "step": 215
+    },
+    {
+      "epoch": 2.2931937172774868,
+      "grad_norm": 1.5239359140396118,
+      "learning_rate": 2.965201256151462e-05,
+      "loss": 0.9081,
+      "step": 220
+    },
+    {
+      "epoch": 2.345549738219895,
+      "grad_norm": 1.6345692873001099,
+      "learning_rate": 2.962350360921145e-05,
+      "loss": 0.9176,
+      "step": 225
+    },
+    {
+      "epoch": 2.3979057591623034,
+      "grad_norm": 1.689063310623169,
+      "learning_rate": 2.959388718163786e-05,
+      "loss": 0.9204,
+      "step": 230
+    },
+    {
+      "epoch": 2.450261780104712,
+      "grad_norm": 1.674101710319519,
+      "learning_rate": 2.956316552172155e-05,
+      "loss": 0.902,
+      "step": 235
+    },
+    {
+      "epoch": 2.5026178010471205,
+      "grad_norm": 1.5287467241287231,
+      "learning_rate": 2.9531340956092274e-05,
+      "loss": 0.8586,
+      "step": 240
+    },
+    {
+      "epoch": 2.554973821989529,
+      "grad_norm": 2.18404221534729,
+      "learning_rate": 2.949841589490564e-05,
+      "loss": 0.8622,
+      "step": 245
+    },
+    {
+      "epoch": 2.607329842931937,
+      "grad_norm": 1.5042572021484375,
+      "learning_rate": 2.946439283166062e-05,
+      "loss": 0.8756,
+      "step": 250
+    },
+    {
+      "epoch": 2.6596858638743455,
+      "grad_norm": 2.0477566719055176,
+      "learning_rate": 2.9429274343010673e-05,
+      "loss": 0.8545,
+      "step": 255
+    },
+    {
+      "epoch": 2.712041884816754,
+      "grad_norm": 2.157820701599121,
+      "learning_rate": 2.939306308856862e-05,
+      "loss": 0.8528,
+      "step": 260
+    },
+    {
+      "epoch": 2.7643979057591626,
+      "grad_norm": 1.9966859817504883,
+      "learning_rate": 2.9355761810705226e-05,
+      "loss": 0.7391,
+      "step": 265
+    },
+    {
+      "epoch": 2.816753926701571,
+      "grad_norm": 1.804949164390564,
+      "learning_rate": 2.9317373334341517e-05,
+      "loss": 0.8296,
+      "step": 270
+    },
+    {
+      "epoch": 2.869109947643979,
+      "grad_norm": 1.699697494506836,
+      "learning_rate": 2.927790056673484e-05,
+      "loss": 0.7829,
+      "step": 275
+    },
+    {
+      "epoch": 2.9214659685863875,
+      "grad_norm": 1.8655725717544556,
+      "learning_rate": 2.923734649725867e-05,
+      "loss": 0.7538,
+      "step": 280
+    },
+    {
+      "epoch": 2.973821989528796,
+      "grad_norm": 1.4555854797363281,
+      "learning_rate": 2.9195714197176257e-05,
+      "loss": 0.7592,
+      "step": 285
+    },
+    {
+      "epoch": 3.020942408376963,
+      "grad_norm": 2.564462423324585,
+      "learning_rate": 2.915300681940799e-05,
+      "loss": 0.7199,
+      "step": 290
+    },
+    {
+      "epoch": 3.073298429319372,
+      "grad_norm": 1.9834420680999756,
+      "learning_rate": 2.9109227598292652e-05,
+      "loss": 0.6972,
+      "step": 295
+    },
+    {
+      "epoch": 3.1256544502617802,
+      "grad_norm": 1.7629621028900146,
+      "learning_rate": 2.9064379849342442e-05,
+      "loss": 0.6761,
+      "step": 300
+    },
+    {
+      "epoch": 3.1780104712041886,
+      "grad_norm": 2.1529428958892822,
+      "learning_rate": 2.9018466968991913e-05,
+      "loss": 0.6594,
+      "step": 305
+    },
+    {
+      "epoch": 3.230366492146597,
+      "grad_norm": 2.405747890472412,
+      "learning_rate": 2.8971492434340738e-05,
+      "loss": 0.6866,
+      "step": 310
+    },
+    {
+      "epoch": 3.282722513089005,
+      "grad_norm": 2.010468006134033,
+      "learning_rate": 2.8923459802890374e-05,
+      "loss": 0.7012,
+      "step": 315
+    },
+    {
+      "epoch": 3.3350785340314135,
+      "grad_norm": 2.1201961040496826,
+      "learning_rate": 2.8874372712274663e-05,
+      "loss": 0.6372,
+      "step": 320
+    },
+    {
+      "epoch": 3.387434554973822,
+      "grad_norm": 1.6618250608444214,
+      "learning_rate": 2.882423487998432e-05,
+      "loss": 0.6968,
+      "step": 325
+    },
+    {
+      "epoch": 3.4397905759162306,
+      "grad_norm": 2.3359334468841553,
+      "learning_rate": 2.877305010308541e-05,
+      "loss": 0.6412,
+      "step": 330
+    },
+    {
+      "epoch": 3.492146596858639,
+      "grad_norm": 2.0028185844421387,
+      "learning_rate": 2.8720822257931796e-05,
+      "loss": 0.689,
+      "step": 335
+    },
+    {
+      "epoch": 3.5445026178010473,
+      "grad_norm": 2.6226954460144043,
+      "learning_rate": 2.8667555299871564e-05,
+      "loss": 0.6438,
+      "step": 340
+    },
+    {
+      "epoch": 3.5968586387434556,
+      "grad_norm": 1.7858210802078247,
+      "learning_rate": 2.8613253262947457e-05,
+      "loss": 0.6228,
+      "step": 345
+    },
+    {
+      "epoch": 3.649214659685864,
+      "grad_norm": 1.8298466205596924,
+      "learning_rate": 2.8557920259591405e-05,
+      "loss": 0.5912,
+      "step": 350
+    },
+    {
+      "epoch": 3.701570680628272,
+      "grad_norm": 3.579176902770996,
+      "learning_rate": 2.850156048031304e-05,
+      "loss": 0.6164,
+      "step": 355
+    },
+    {
+      "epoch": 3.7539267015706805,
+      "grad_norm": 2.120554208755493,
+      "learning_rate": 2.8444178193382376e-05,
+      "loss": 0.6257,
+      "step": 360
+    },
+    {
+      "epoch": 3.806282722513089,
+      "grad_norm": 2.168713092803955,
+      "learning_rate": 2.8385777744506523e-05,
+      "loss": 0.598,
+      "step": 365
+    },
+    {
+      "epoch": 3.858638743455497,
+      "grad_norm": 1.5940132141113281,
+      "learning_rate": 2.83263635565006e-05,
+      "loss": 0.579,
+      "step": 370
+    },
+    {
+      "epoch": 3.9109947643979055,
+      "grad_norm": 2.5703248977661133,
+      "learning_rate": 2.82659401289528e-05,
+      "loss": 0.582,
+      "step": 375
+    },
+    {
+      "epoch": 3.9633507853403143,
+      "grad_norm": 2.092498779296875,
+      "learning_rate": 2.820451203788357e-05,
+      "loss": 0.5975,
+      "step": 380
+    },
+    {
+      "epoch": 4.010471204188482,
+      "grad_norm": 2.029618978500366,
+      "learning_rate": 2.814208393539911e-05,
+      "loss": 0.5906,
+      "step": 385
+    },
+    {
+      "epoch": 4.06282722513089,
+      "grad_norm": 2.290864944458008,
+      "learning_rate": 2.8078660549339047e-05,
+      "loss": 0.4818,
+      "step": 390
+    },
+    {
+      "epoch": 4.115183246073299,
+      "grad_norm": 1.9988826513290405,
+      "learning_rate": 2.8014246682918345e-05,
+      "loss": 0.5304,
+      "step": 395
+    },
+    {
+      "epoch": 4.167539267015707,
+      "grad_norm": 1.9701881408691406,
+      "learning_rate": 2.794884721436361e-05,
+      "loss": 0.5242,
+      "step": 400
+    },
+    {
+      "epoch": 4.219895287958115,
+      "grad_norm": 2.2701263427734375,
+      "learning_rate": 2.7882467096543585e-05,
+      "loss": 0.5123,
+      "step": 405
+    },
+    {
+      "epoch": 4.272251308900524,
+      "grad_norm": 2.2033908367156982,
+      "learning_rate": 2.781511135659411e-05,
+      "loss": 0.5038,
+      "step": 410
+    },
+    {
+      "epoch": 4.324607329842932,
+      "grad_norm": 2.103170394897461,
+      "learning_rate": 2.7746785095537357e-05,
+      "loss": 0.5031,
+      "step": 415
+    },
+    {
+      "epoch": 4.37696335078534,
+      "grad_norm": 2.2560765743255615,
+      "learning_rate": 2.7677493487895556e-05,
+      "loss": 0.5131,
+      "step": 420
+    },
+    {
+      "epoch": 4.429319371727749,
+      "grad_norm": 2.439460515975952,
+      "learning_rate": 2.76072417812991e-05,
+      "loss": 0.5047,
+      "step": 425
+    },
+    {
+      "epoch": 4.481675392670157,
+      "grad_norm": 1.9526431560516357,
+      "learning_rate": 2.7536035296089116e-05,
+      "loss": 0.4999,
+      "step": 430
+    },
+    {
+      "epoch": 4.534031413612565,
+      "grad_norm": 2.111056327819824,
+      "learning_rate": 2.746387942491456e-05,
+      "loss": 0.5154,
+      "step": 435
+    },
+    {
+      "epoch": 4.5863874345549736,
+      "grad_norm": 2.7262227535247803,
+      "learning_rate": 2.7390779632323815e-05,
+      "loss": 0.4889,
+      "step": 440
+    },
+    {
+      "epoch": 4.638743455497382,
+      "grad_norm": 2.0161452293395996,
+      "learning_rate": 2.7316741454350832e-05,
+      "loss": 0.4876,
+      "step": 445
+    },
+    {
+      "epoch": 4.69109947643979,
+      "grad_norm": 2.179011106491089,
+      "learning_rate": 2.7241770498095897e-05,
+      "loss": 0.4789,
+      "step": 450
+    },
+    {
+      "epoch": 4.7434554973821985,
+      "grad_norm": 2.0215184688568115,
+      "learning_rate": 2.7165872441300964e-05,
+      "loss": 0.4736,
+      "step": 455
+    },
+    {
+      "epoch": 4.795811518324607,
+      "grad_norm": 1.9461724758148193,
+      "learning_rate": 2.708905303191969e-05,
+      "loss": 0.4754,
+      "step": 460
+    },
+    {
+      "epoch": 4.848167539267016,
+      "grad_norm": 2.405299425125122,
+      "learning_rate": 2.7011318087682112e-05,
+      "loss": 0.4755,
+      "step": 465
+    },
+    {
+      "epoch": 4.900523560209424,
+      "grad_norm": 2.1616289615631104,
+      "learning_rate": 2.693267349565405e-05,
+      "loss": 0.4488,
+      "step": 470
+    },
+    {
+      "epoch": 4.952879581151833,
+      "grad_norm": 2.4113879203796387,
+      "learning_rate": 2.6853125211791292e-05,
+      "loss": 0.4203,
+      "step": 475
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.0132861137390137,
+      "learning_rate": 2.6772679260488504e-05,
+      "loss": 0.4389,
+      "step": 480
+    },
+    {
+      "epoch": 5.052356020942408,
+      "grad_norm": 2.1897664070129395,
+      "learning_rate": 2.6691341734122997e-05,
+      "loss": 0.4233,
+      "step": 485
+    },
+    {
+      "epoch": 5.104712041884817,
+      "grad_norm": 2.008359909057617,
+      "learning_rate": 2.660911879259335e-05,
+      "loss": 0.3524,
+      "step": 490
+    },
+    {
+      "epoch": 5.157068062827225,
+      "grad_norm": 2.1782288551330566,
+      "learning_rate": 2.6526016662852887e-05,
+      "loss": 0.3928,
+      "step": 495
+    },
+    {
+      "epoch": 5.209424083769633,
+      "grad_norm": 2.0432088375091553,
+      "learning_rate": 2.6442041638438098e-05,
+      "loss": 0.3928,
+      "step": 500
+    },
+    {
+      "epoch": 5.261780104712042,
+      "grad_norm": 2.686347723007202,
+      "learning_rate": 2.635720007899201e-05,
+      "loss": 0.388,
+      "step": 505
+    },
+    {
+      "epoch": 5.31413612565445,
+      "grad_norm": 2.0326364040374756,
+      "learning_rate": 2.6271498409782582e-05,
+      "loss": 0.3846,
+      "step": 510
+    },
+    {
+      "epoch": 5.366492146596858,
+      "grad_norm": 1.9769495725631714,
+      "learning_rate": 2.6184943121216058e-05,
+      "loss": 0.3545,
+      "step": 515
+    },
+    {
+      "epoch": 5.418848167539267,
+      "grad_norm": 2.249706268310547,
+      "learning_rate": 2.6097540768345472e-05,
+      "loss": 0.3698,
+      "step": 520
+    },
+    {
+      "epoch": 5.471204188481676,
+      "grad_norm": 1.8810491561889648,
+      "learning_rate": 2.600929797037419e-05,
+      "loss": 0.4005,
+      "step": 525
+    },
+    {
+      "epoch": 5.523560209424084,
+      "grad_norm": 2.422290802001953,
+      "learning_rate": 2.592022141015464e-05,
+      "loss": 0.3855,
+      "step": 530
+    },
+    {
+      "epoch": 5.575916230366492,
+      "grad_norm": 2.183039665222168,
+      "learning_rate": 2.5830317833682186e-05,
+      "loss": 0.354,
+      "step": 535
+    },
+    {
+      "epoch": 5.628272251308901,
+      "grad_norm": 1.920445203781128,
+      "learning_rate": 2.5739594049584255e-05,
+      "loss": 0.3601,
+      "step": 540
+    },
+    {
+      "epoch": 5.680628272251309,
+      "grad_norm": 2.186728000640869,
+      "learning_rate": 2.5648056928604682e-05,
+      "loss": 0.3806,
+      "step": 545
+    },
+    {
+      "epoch": 5.732984293193717,
+      "grad_norm": 2.2915523052215576,
+      "learning_rate": 2.5555713403083385e-05,
+      "loss": 0.3591,
+      "step": 550
+    },
+    {
+      "epoch": 5.785340314136126,
+      "grad_norm": 2.1855974197387695,
+      "learning_rate": 2.546257046643136e-05,
+      "loss": 0.377,
+      "step": 555
+    },
+    {
+      "epoch": 5.837696335078534,
+      "grad_norm": 2.0636916160583496,
+      "learning_rate": 2.536863517260104e-05,
+      "loss": 0.3678,
+      "step": 560
+    },
+    {
+      "epoch": 5.890052356020942,
+      "grad_norm": 2.7312142848968506,
+      "learning_rate": 2.52739146355521e-05,
+      "loss": 0.3922,
+      "step": 565
+    },
+    {
+      "epoch": 5.942408376963351,
+      "grad_norm": 1.9910225868225098,
+      "learning_rate": 2.5178416028712692e-05,
+      "loss": 0.3741,
+      "step": 570
+    },
+    {
+      "epoch": 5.994764397905759,
+      "grad_norm": 2.068664312362671,
+      "learning_rate": 2.5082146584436166e-05,
+      "loss": 0.3749,
+      "step": 575
+    },
+    {
+      "epoch": 6.041884816753926,
+      "grad_norm": 2.0572855472564697,
+      "learning_rate": 2.4985113593453365e-05,
+      "loss": 0.2834,
+      "step": 580
+    },
+    {
+      "epoch": 6.0942408376963355,
+      "grad_norm": 2.303874969482422,
+      "learning_rate": 2.488732440432049e-05,
+      "loss": 0.2875,
+      "step": 585
+    },
+    {
+      "epoch": 6.146596858638744,
+      "grad_norm": 2.420100212097168,
+      "learning_rate": 2.478878642286253e-05,
+      "loss": 0.2938,
+      "step": 590
+    },
+    {
+      "epoch": 6.198952879581152,
+      "grad_norm": 1.8585245609283447,
+      "learning_rate": 2.4689507111612455e-05,
+      "loss": 0.299,
+      "step": 595
+    },
+    {
+      "epoch": 6.2513089005235605,
+      "grad_norm": 2.8291428089141846,
+      "learning_rate": 2.458949398924601e-05,
+      "loss": 0.2928,
+      "step": 600
+    },
+    {
+      "epoch": 6.303664921465969,
+      "grad_norm": 1.6938339471817017,
+      "learning_rate": 2.448875463001236e-05,
+      "loss": 0.2984,
+      "step": 605
+    },
+    {
+      "epoch": 6.356020942408377,
+      "grad_norm": 2.571981191635132,
+      "learning_rate": 2.438729666316041e-05,
+      "loss": 0.3253,
+      "step": 610
+    },
+    {
+      "epoch": 6.408376963350785,
+      "grad_norm": 2.0141608715057373,
+      "learning_rate": 2.4285127772361077e-05,
+      "loss": 0.2898,
+      "step": 615
+    },
+    {
+      "epoch": 6.460732984293194,
+      "grad_norm": 2.1542282104492188,
+      "learning_rate": 2.4182255695125344e-05,
+      "loss": 0.3346,
+      "step": 620
+    },
+    {
+      "epoch": 6.513089005235602,
+      "grad_norm": 2.03896164894104,
+      "learning_rate": 2.407868822221833e-05,
+      "loss": 0.3246,
+      "step": 625
+    },
+    {
+      "epoch": 6.56544502617801,
+      "grad_norm": 2.094012975692749,
+      "learning_rate": 2.3974433197069207e-05,
+      "loss": 0.3111,
+      "step": 630
+    },
+    {
+      "epoch": 6.617801047120419,
+      "grad_norm": 2.2046549320220947,
+      "learning_rate": 2.386949851517726e-05,
+      "loss": 0.2865,
+      "step": 635
+    },
+    {
+      "epoch": 6.670157068062827,
+      "grad_norm": 2.1831257343292236,
+      "learning_rate": 2.376389212351391e-05,
+      "loss": 0.3207,
+      "step": 640
+    },
+    {
+      "epoch": 6.722513089005235,
+      "grad_norm": 1.9105017185211182,
+      "learning_rate": 2.3657622019920865e-05,
+      "loss": 0.3207,
+      "step": 645
+    },
+    {
+      "epoch": 6.774869109947644,
+      "grad_norm": 2.251492738723755,
+      "learning_rate": 2.3550696252504435e-05,
+      "loss": 0.3073,
+      "step": 650
+    },
+    {
+      "epoch": 6.827225130890052,
+      "grad_norm": 2.173784017562866,
+      "learning_rate": 2.3443122919026034e-05,
+      "loss": 0.3105,
+      "step": 655
+    },
+    {
+      "epoch": 6.879581151832461,
+      "grad_norm": 2.0459015369415283,
+      "learning_rate": 2.3334910166288898e-05,
+      "loss": 0.3132,
+      "step": 660
+    },
+    {
+      "epoch": 6.9319371727748695,
+      "grad_norm": 2.2690305709838867,
+      "learning_rate": 2.3226066189521123e-05,
+      "loss": 0.2815,
+      "step": 665
+    },
+    {
+      "epoch": 6.984293193717278,
+      "grad_norm": 1.8328899145126343,
+      "learning_rate": 2.3116599231755017e-05,
+      "loss": 0.2743,
+      "step": 670
+    },
+    {
+      "epoch": 7.031413612565445,
+      "grad_norm": 1.8480794429779053,
+      "learning_rate": 2.3006517583202808e-05,
+      "loss": 0.2538,
+      "step": 675
+    },
+    {
+      "epoch": 7.0837696335078535,
+      "grad_norm": 1.5677030086517334,
+      "learning_rate": 2.289582958062885e-05,
+      "loss": 0.2663,
+      "step": 680
+    },
+    {
+      "epoch": 7.136125654450262,
+      "grad_norm": 1.777860164642334,
+      "learning_rate": 2.2784543606718227e-05,
+      "loss": 0.2417,
+      "step": 685
+    },
+    {
+      "epoch": 7.18848167539267,
+      "grad_norm": 2.3644204139709473,
+      "learning_rate": 2.267266808944192e-05,
+      "loss": 0.2598,
+      "step": 690
+    },
+    {
+      "epoch": 7.2408376963350785,
+      "grad_norm": 1.845493197441101,
+      "learning_rate": 2.2560211501418525e-05,
+      "loss": 0.2524,
+      "step": 695
+    },
+    {
+      "epoch": 7.293193717277487,
+      "grad_norm": 2.1028873920440674,
+      "learning_rate": 2.2447182359272635e-05,
+      "loss": 0.2325,
+      "step": 700
+    },
+    {
+      "epoch": 7.345549738219895,
+      "grad_norm": 2.070425033569336,
+      "learning_rate": 2.2333589222989798e-05,
+      "loss": 0.2503,
+      "step": 705
+    },
+    {
+      "epoch": 7.397905759162303,
+      "grad_norm": 2.3109984397888184,
+      "learning_rate": 2.2219440695268294e-05,
+      "loss": 0.2597,
+      "step": 710
+    },
+    {
+      "epoch": 7.450261780104712,
+      "grad_norm": 2.202803134918213,
+      "learning_rate": 2.2104745420867624e-05,
+      "loss": 0.2347,
+      "step": 715
+    },
+    {
+      "epoch": 7.50261780104712,
+      "grad_norm": 1.9535624980926514,
+      "learning_rate": 2.1989512085953793e-05,
+      "loss": 0.2584,
+      "step": 720
+    },
+    {
+      "epoch": 7.554973821989529,
+      "grad_norm": 2.0640347003936768,
+      "learning_rate": 2.18737494174415e-05,
+      "loss": 0.2595,
+      "step": 725
+    },
+    {
+      "epoch": 7.607329842931938,
+      "grad_norm": 1.6874743700027466,
+      "learning_rate": 2.1757466182333254e-05,
+      "loss": 0.2544,
+      "step": 730
+    },
+    {
+      "epoch": 7.659685863874346,
+      "grad_norm": 1.7148810625076294,
+      "learning_rate": 2.1640671187055383e-05,
+      "loss": 0.258,
+      "step": 735
+    },
+    {
+      "epoch": 7.712041884816754,
+      "grad_norm": 1.8402714729309082,
+      "learning_rate": 2.152337327679112e-05,
+      "loss": 0.2581,
+      "step": 740
+    },
+    {
+      "epoch": 7.7643979057591626,
+      "grad_norm": 2.2578415870666504,
+      "learning_rate": 2.140558133481074e-05,
+      "loss": 0.2474,
+      "step": 745
+    },
+    {
+      "epoch": 7.816753926701571,
+      "grad_norm": 1.9558266401290894,
+      "learning_rate": 2.1287304281798794e-05,
+      "loss": 0.2247,
+      "step": 750
+    },
+    {
+      "epoch": 7.869109947643979,
+      "grad_norm": 2.2188961505889893,
+      "learning_rate": 2.1168551075178543e-05,
+      "loss": 0.2303,
+      "step": 755
+    },
+    {
+      "epoch": 7.9214659685863875,
+      "grad_norm": 1.9665825366973877,
+      "learning_rate": 2.1049330708433563e-05,
+      "loss": 0.2477,
+      "step": 760
+    },
+    {
+      "epoch": 7.973821989528796,
+      "grad_norm": 2.1581296920776367,
+      "learning_rate": 2.0929652210426663e-05,
+      "loss": 0.2244,
+      "step": 765
+    },
+    {
+      "epoch": 8.020942408376964,
+      "grad_norm": 2.0662615299224854,
+      "learning_rate": 2.0809524644716106e-05,
+      "loss": 0.2146,
+      "step": 770
+    },
+    {
+      "epoch": 8.073298429319372,
+      "grad_norm": 2.4462475776672363,
+      "learning_rate": 2.0688957108869203e-05,
+      "loss": 0.2059,
+      "step": 775
+    },
+    {
+      "epoch": 8.12565445026178,
+      "grad_norm": 1.8161300420761108,
+      "learning_rate": 2.056795873377331e-05,
+      "loss": 0.218,
+      "step": 780
+    },
+    {
+      "epoch": 8.178010471204189,
+      "grad_norm": 1.6970865726470947,
+      "learning_rate": 2.044653868294436e-05,
+      "loss": 0.2058,
+      "step": 785
+    },
+    {
+      "epoch": 8.230366492146597,
+      "grad_norm": 2.00407075881958,
+      "learning_rate": 2.0324706151832853e-05,
+      "loss": 0.2195,
+      "step": 790
+    },
+    {
+      "epoch": 8.282722513089006,
+      "grad_norm": 2.514988899230957,
+      "learning_rate": 2.0202470367127477e-05,
+      "loss": 0.2239,
+      "step": 795
+    },
+    {
+      "epoch": 8.335078534031414,
+      "grad_norm": 2.4687931537628174,
+      "learning_rate": 2.0079840586056343e-05,
+      "loss": 0.1918,
+      "step": 800
+    },
+    {
+      "epoch": 8.387434554973822,
+      "grad_norm": 1.8812583684921265,
+      "learning_rate": 1.9956826095685917e-05,
+      "loss": 0.2086,
+      "step": 805
+    },
+    {
+      "epoch": 8.43979057591623,
+      "grad_norm": 1.6383140087127686,
+      "learning_rate": 1.9833436212217682e-05,
+      "loss": 0.2052,
+      "step": 810
+    },
+    {
+      "epoch": 8.492146596858639,
+      "grad_norm": 2.128833055496216,
+      "learning_rate": 1.9709680280282593e-05,
+      "loss": 0.2187,
+      "step": 815
+    },
+    {
+      "epoch": 8.544502617801047,
+      "grad_norm": 1.8959410190582275,
+      "learning_rate": 1.9585567672233398e-05,
+      "loss": 0.2092,
+      "step": 820
+    },
+    {
+      "epoch": 8.596858638743456,
+      "grad_norm": 1.8595294952392578,
+      "learning_rate": 1.9461107787434833e-05,
+      "loss": 0.1996,
+      "step": 825
+    },
+    {
+      "epoch": 8.649214659685864,
+      "grad_norm": 1.96145498752594,
+      "learning_rate": 1.9336310051551788e-05,
+      "loss": 0.217,
+      "step": 830
+    },
+    {
+      "epoch": 8.701570680628272,
+      "grad_norm": 1.8644137382507324,
+      "learning_rate": 1.9211183915835492e-05,
+      "loss": 0.2105,
+      "step": 835
+    },
+    {
+      "epoch": 8.75392670157068,
+      "grad_norm": 2.339465618133545,
+      "learning_rate": 1.9085738856407708e-05,
+      "loss": 0.211,
+      "step": 840
+    },
+    {
+      "epoch": 8.806282722513089,
+      "grad_norm": 1.9026511907577515,
+      "learning_rate": 1.895998437354312e-05,
+      "loss": 0.2338,
+      "step": 845
+    },
+    {
+      "epoch": 8.858638743455497,
+      "grad_norm": 2.136833906173706,
+      "learning_rate": 1.883392999094984e-05,
+      "loss": 0.2332,
+      "step": 850
+    },
+    {
+      "epoch": 8.910994764397905,
+      "grad_norm": 2.0453922748565674,
+      "learning_rate": 1.8707585255048152e-05,
+      "loss": 0.1852,
+      "step": 855
+    },
+    {
+      "epoch": 8.963350785340314,
+      "grad_norm": 2.331050157546997,
+      "learning_rate": 1.8580959734247537e-05,
+      "loss": 0.193,
+      "step": 860
+    },
+    {
+      "epoch": 9.010471204188482,
+      "grad_norm": 2.5257890224456787,
+      "learning_rate": 1.8454063018222022e-05,
+      "loss": 0.2143,
+      "step": 865
+    },
+    {
+      "epoch": 9.06282722513089,
+      "grad_norm": 1.800729751586914,
+      "learning_rate": 1.832690471718397e-05,
+      "loss": 0.1547,
+      "step": 870
+    },
+    {
+      "epoch": 9.115183246073299,
+      "grad_norm": 1.547395944595337,
+      "learning_rate": 1.8199494461156203e-05,
+      "loss": 0.1806,
+      "step": 875
+    },
+    {
+      "epoch": 9.167539267015707,
+      "grad_norm": 1.5873461961746216,
+      "learning_rate": 1.8071841899242775e-05,
+      "loss": 0.1745,
+      "step": 880
+    },
+    {
+      "epoch": 9.219895287958115,
+      "grad_norm": 1.8685342073440552,
+      "learning_rate": 1.7943956698898167e-05,
+      "loss": 0.1788,
+      "step": 885
+    },
+    {
+      "epoch": 9.272251308900524,
+      "grad_norm": 2.1903324127197266,
+      "learning_rate": 1.781584854519516e-05,
+      "loss": 0.1856,
+      "step": 890
+    },
+    {
+      "epoch": 9.324607329842932,
+      "grad_norm": 1.6244503259658813,
+      "learning_rate": 1.7687527140091365e-05,
+      "loss": 0.1702,
+      "step": 895
+    },
+    {
+      "epoch": 9.37696335078534,
+      "grad_norm": 2.138651132583618,
+      "learning_rate": 1.755900220169448e-05,
+      "loss": 0.1927,
+      "step": 900
+    },
+    {
+      "epoch": 9.429319371727749,
+      "grad_norm": 1.89018976688385,
+      "learning_rate": 1.743028346352627e-05,
+      "loss": 0.1828,
+      "step": 905
+    },
+    {
+      "epoch": 9.481675392670157,
+      "grad_norm": 1.7095950841903687,
+      "learning_rate": 1.7301380673785486e-05,
+      "loss": 0.192,
+      "step": 910
+    },
+    {
+      "epoch": 9.534031413612565,
+      "grad_norm": 2.298391103744507,
+      "learning_rate": 1.7172303594609543e-05,
+      "loss": 0.1727,
+      "step": 915
+    },
+    {
+      "epoch": 9.586387434554974,
+      "grad_norm": 2.142773389816284,
+      "learning_rate": 1.704306200133526e-05,
+      "loss": 0.1825,
+      "step": 920
+    },
+    {
+      "epoch": 9.638743455497382,
+      "grad_norm": 1.678457498550415,
+      "learning_rate": 1.6913665681758518e-05,
+      "loss": 0.1866,
+      "step": 925
+    },
+    {
+      "epoch": 9.69109947643979,
+      "grad_norm": 1.5535097122192383,
+      "learning_rate": 1.6784124435393034e-05,
+      "loss": 0.1916,
+      "step": 930
+    },
+    {
+      "epoch": 9.743455497382199,
+      "grad_norm": 1.5964089632034302,
+      "learning_rate": 1.6654448072728165e-05,
+      "loss": 0.1726,
+      "step": 935
+    },
+    {
+      "epoch": 9.795811518324607,
+      "grad_norm": 2.015465497970581,
+      "learning_rate": 1.652464641448601e-05,
+      "loss": 0.1914,
+      "step": 940
+    },
+    {
+      "epoch": 9.848167539267015,
+      "grad_norm": 2.025540351867676,
+      "learning_rate": 1.6394729290877606e-05,
+      "loss": 0.1784,
+      "step": 945
+    },
+    {
+      "epoch": 9.900523560209423,
+      "grad_norm": 1.693466067314148,
+      "learning_rate": 1.6264706540858465e-05,
+      "loss": 0.1731,
+      "step": 950
+    },
+    {
+      "epoch": 9.952879581151832,
+      "grad_norm": 2.2833855152130127,
+      "learning_rate": 1.6134588011383472e-05,
+      "loss": 0.2008,
+      "step": 955
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 2.3272955417633057,
+      "learning_rate": 1.600438355666113e-05,
+      "loss": 0.1861,
+      "step": 960
+    },
+    {
+      "epoch": 10.052356020942408,
+      "grad_norm": 1.6399215459823608,
+      "learning_rate": 1.5874103037407288e-05,
+      "loss": 0.159,
+      "step": 965
+    },
+    {
+      "epoch": 10.104712041884817,
+      "grad_norm": 1.7252026796340942,
+      "learning_rate": 1.5743756320098334e-05,
+      "loss": 0.166,
+      "step": 970
+    },
+    {
+      "epoch": 10.157068062827225,
+      "grad_norm": 1.4673538208007812,
+      "learning_rate": 1.5613353276224034e-05,
+      "loss": 0.1595,
+      "step": 975
+    },
+    {
+      "epoch": 10.209424083769633,
+      "grad_norm": 1.8614445924758911,
+      "learning_rate": 1.5482903781539887e-05,
+      "loss": 0.1635,
+      "step": 980
+    },
+    {
+      "epoch": 10.261780104712042,
+      "grad_norm": 1.6224993467330933,
+      "learning_rate": 1.5352417715319235e-05,
+      "loss": 0.157,
+      "step": 985
+    },
+    {
+      "epoch": 10.31413612565445,
+      "grad_norm": 1.548218846321106,
+      "learning_rate": 1.5221904959605081e-05,
+      "loss": 0.1755,
+      "step": 990
+    },
+    {
+      "epoch": 10.366492146596858,
+      "grad_norm": 1.4170892238616943,
+      "learning_rate": 1.509137539846169e-05,
+      "loss": 0.1556,
+      "step": 995
+    },
+    {
+      "epoch": 10.418848167539267,
+      "grad_norm": 1.7958966493606567,
+      "learning_rate": 1.4960838917226034e-05,
+      "loss": 0.1658,
+      "step": 1000
+    },
+    {
+      "epoch": 10.471204188481675,
+      "grad_norm": 1.8197486400604248,
+      "learning_rate": 1.483030540175918e-05,
+      "loss": 0.1634,
+      "step": 1005
+    },
+    {
+      "epoch": 10.523560209424083,
+      "grad_norm": 1.8356825113296509,
+      "learning_rate": 1.4699784737697583e-05,
+      "loss": 0.1673,
+      "step": 1010
+    },
+    {
+      "epoch": 10.575916230366492,
+      "grad_norm": 1.7088730335235596,
+      "learning_rate": 1.4569286809704406e-05,
+      "loss": 0.1643,
+      "step": 1015
+    },
+    {
+      "epoch": 10.6282722513089,
+      "grad_norm": 1.756155252456665,
+      "learning_rate": 1.4438821500720998e-05,
+      "loss": 0.1644,
+      "step": 1020
+    },
+    {
+      "epoch": 10.680628272251308,
+      "grad_norm": 1.9680912494659424,
+      "learning_rate": 1.4308398691218341e-05,
+      "loss": 0.1625,
+      "step": 1025
+    },
+    {
+      "epoch": 10.732984293193716,
+      "grad_norm": 1.5771136283874512,
+      "learning_rate": 1.417802825844885e-05,
+      "loss": 0.1751,
+      "step": 1030
+    },
+    {
+      "epoch": 10.785340314136125,
+      "grad_norm": 1.76025390625,
+      "learning_rate": 1.4047720075698302e-05,
+      "loss": 0.164,
+      "step": 1035
+    },
+    {
+      "epoch": 10.837696335078533,
+      "grad_norm": 2.363912343978882,
+      "learning_rate": 1.3917484011538135e-05,
+      "loss": 0.1554,
+      "step": 1040
+    },
+    {
+      "epoch": 10.890052356020943,
+      "grad_norm": 1.7519829273223877,
+      "learning_rate": 1.378732992907805e-05,
+      "loss": 0.1676,
+      "step": 1045
+    },
+    {
+      "epoch": 10.942408376963352,
+      "grad_norm": 1.434294581413269,
+      "learning_rate": 1.3657267685219072e-05,
+      "loss": 0.1353,
+      "step": 1050
+    },
+    {
+      "epoch": 10.99476439790576,
+      "grad_norm": 1.4985880851745605,
+      "learning_rate": 1.3527307129907049e-05,
+      "loss": 0.1487,
+      "step": 1055
+    },
+    {
+      "epoch": 11.041884816753926,
+      "grad_norm": 2.3242697715759277,
+      "learning_rate": 1.3397458105386687e-05,
+      "loss": 0.1346,
+      "step": 1060
+    },
+    {
+      "epoch": 11.094240837696335,
+      "grad_norm": 1.361412763595581,
+      "learning_rate": 1.3267730445456208e-05,
+      "loss": 0.1309,
+      "step": 1065
+    },
+    {
+      "epoch": 11.146596858638743,
+      "grad_norm": 1.981557011604309,
+      "learning_rate": 1.3138133974722565e-05,
+      "loss": 0.1498,
+      "step": 1070
+    },
+    {
+      "epoch": 11.198952879581151,
+      "grad_norm": 1.580352783203125,
+      "learning_rate": 1.3008678507857409e-05,
+      "loss": 0.1514,
+      "step": 1075
+    },
+    {
+      "epoch": 11.25130890052356,
+      "grad_norm": 1.8594692945480347,
+      "learning_rate": 1.2879373848853823e-05,
+      "loss": 0.128,
+      "step": 1080
+    },
+    {
+      "epoch": 11.303664921465968,
+      "grad_norm": 1.7048500776290894,
+      "learning_rate": 1.2750229790283827e-05,
+      "loss": 0.1303,
+      "step": 1085
+    },
+    {
+      "epoch": 11.356020942408376,
+      "grad_norm": 1.8332265615463257,
+      "learning_rate": 1.2621256112556749e-05,
+      "loss": 0.1618,
+      "step": 1090
+    },
+    {
+      "epoch": 11.408376963350785,
+      "grad_norm": 1.482491374015808,
+      "learning_rate": 1.2492462583178547e-05,
+      "loss": 0.1543,
+      "step": 1095
+    },
+    {
+      "epoch": 11.460732984293193,
+      "grad_norm": 1.6219063997268677,
+      "learning_rate": 1.2363858956012081e-05,
+      "loss": 0.1592,
+      "step": 1100
+    },
+    {
+      "epoch": 11.513089005235603,
+      "grad_norm": 1.3748217821121216,
+      "learning_rate": 1.2235454970538443e-05,
+      "loss": 0.133,
+      "step": 1105
+    },
+    {
+      "epoch": 11.565445026178011,
+      "grad_norm": 1.405530571937561,
+      "learning_rate": 1.2107260351119332e-05,
+      "loss": 0.1429,
+      "step": 1110
+    },
+    {
+      "epoch": 11.61780104712042,
+      "grad_norm": 1.73845636844635,
+      "learning_rate": 1.1979284806260639e-05,
+      "loss": 0.1356,
+      "step": 1115
+    },
+    {
+      "epoch": 11.670157068062828,
+      "grad_norm": 1.249050498008728,
+      "learning_rate": 1.1851538027877154e-05,
+      "loss": 0.1356,
+      "step": 1120
+    },
+    {
+      "epoch": 11.722513089005236,
+      "grad_norm": 1.714762806892395,
+      "learning_rate": 1.172402969055863e-05,
+      "loss": 0.1277,
+      "step": 1125
+    },
+    {
+      "epoch": 11.774869109947645,
+      "grad_norm": 1.4738872051239014,
+      "learning_rate": 1.1596769450837054e-05,
+      "loss": 0.1562,
+      "step": 1130
+    },
+    {
+      "epoch": 11.827225130890053,
+      "grad_norm": 1.605211615562439,
+      "learning_rate": 1.1469766946455337e-05,
+      "loss": 0.1787,
+      "step": 1135
+    },
+    {
+      "epoch": 11.879581151832461,
+      "grad_norm": 1.681419849395752,
+      "learning_rate": 1.134303179563744e-05,
+      "loss": 0.1474,
+      "step": 1140
+    },
+    {
+      "epoch": 11.93193717277487,
+      "grad_norm": 1.2794703245162964,
+      "learning_rate": 1.1216573596359984e-05,
+      "loss": 0.1609,
+      "step": 1145
+    },
+    {
+      "epoch": 11.984293193717278,
+      "grad_norm": 1.6714304685592651,
+      "learning_rate": 1.10904019256253e-05,
+      "loss": 0.1401,
+      "step": 1150
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.2770695473659904e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c70bca501007d7886eed27b5fce908bf9eeef36b2f006f1a19cae3b7227bd0b5
+size 7608

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1152/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/Llama-3.1-8B
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-8B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4daf7a872eede5dfb63419e082cb790ff143368673a1ce1dd2b94355c1ba73dc
+size 1342239008

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/latest

@@ -0,0 +1 @@
+global_step1241

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:730ea413fb7e47233d90b37c3e996b6662c1514a3ebd97b8c7dc2b466a02ac7b
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a811aa0d4ca5e6c6e481c27e8da3b400c02103a9a35b0117d4e71bac10cba31f
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeb37ac40eaad29f560e710168e90f237efdd0a484bd9001e6559d680e3b5b8a
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd998041c8a61d5b1e9f093e3e31c2fcfbefb5ac578e070599cd7be91bf269d5
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1640eb06d73ad9b46be22057c151d215b1c350f351386abef3e01f1df10ed72
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed028e6f6b6820daef99d7984d36c7f37d4c680bd0cefb9cf9d353620f6d1f87
+size 15920

group_size_117/layer_full/512/base/0_256_e20_3e-5/checkpoint-1248/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ba7d37ea7e639ec15cb0a88839f8bf465899cb56f91dd29268aa2da62b02a4
+size 15920